A Predictive Approach to Roadway Departure Prevention
نویسندگان
چکیده
In this paper, we investigate predictive control approaches to the problem of roadway departure prevention via steering and braking. We assume a sensing infrastructure detecting road geometry and consider a two layers architecture consisting of a threat assessment and an intervention layer. In particular, the upper threat assessment layer detects the risk of roadway departure or vehicle instability within a future time horizon. If a risk of roadway departure or vehicle instability is detected, the lower intervention layer is enabled. The latter is designed based on Model Predictive Control (MPC) approaches, where steering and braking interventions are the result of an optimization problem. This is formulated on the basis of vehicle state measurements and coming road information (e.g., road geometry, surface adhesion) and repeatedly solved over a moving future time horizon. Simulation and experimental results are presented, showing that the proposed approach effectively exploits road preview capabilities in order to issue earlier and less intrusive interventions, compared to standard Electronic Stability Control (ESC) systems.
منابع مشابه
Semi-Autonomous Vehicle Control for Road Departure and Obstacle Avoidance
This paper presents an active safety system for avoiding obstacles and preventing road departures by means of assistance in steering and braking. A Nonlinear Model Predictive Controller (NMPC) is designed with the goal of using the minimum control intervention to keep the driver safe. The NMPC uses a nonlinear vehicle and driver steering model to predict a collision or a roadway departure. The ...
متن کاملPredicting Lane Position for Roadway Departure Prevention
In this paper, we describe a preliminary analysis of driver data collected during a recently completed small scale data collection effort. We will demonstrate that a popular method for computing Time To Lane Crossing (TLC) does not always accurately predict the driver's actual TLC. We will then use a memory based learning approach to show why this is. Finally, we will present results in predict...
متن کاملAURORA: a vision-based roadway departure warning system
AURORA is a vision-based system designed to warn a vehicle driver of possible impending roadway departure accidents. It employs a downward looking color video camera with a wide angle lens, a digitizer, and a portable Sun Sparc workstation. Using a binormalized adjustable template correlation algorithm, it reliably detects lane markers on structured roads at 60 Hz. A time-to-lanecrossing (TLC) ...
متن کاملImproving Data accuracy of roadway Departure crashes: Practice in Virginia, uSa, and Its national Implications
In this paper by Past President’s Award for Merit in Transportation recipient Ning Li and coauthor Stephen W. Read, a serious issue is raised in current roadway departure (RD) crash research and practices. Despite the importance of RD crashes, the definitions and identification methods of the RD crashes are inconsistent, and significant differences exist in the reported RD crash deaths between ...
متن کامل